Path: utzoo!censor!geac!torsqnt!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!news.cs.indiana.edu!att!rutgers!njin!uupsi!sunic!nuug!sigyn.idt.unit.no!ugle.unit.no!hanche
From: hanche@imf.unit.no (Harald Hanche-Olsen)
Newsgroups: comp.sys.apollo
Subject: Re: DN10000 disk space
Message-ID: <HANCHE.90Dec7184829@hufsa.imf.unit.no>
Date: 7 Dec 90 17:48:29 GMT
References: <90Dec6.172904est.57368@ugw.utcs.utoronto.ca>
	<1990Dec7.034301.29493@midway.uchicago.edu>
Sender: news@ugle.unit.no
Organization: The Norwegian Institute of Technology, Trondheim, Norway.
Lines: 25
In-Reply-To: rtp1@quads.uchicago.edu's message of 7 Dec 90 03:43:01 GMT

In article <1990Dec7.034301.29493@midway.uchicago.edu> rtp1@quads.uchicago.edu (raymond thomas pierrehumbert) writes:

   I have looked at a lot of machines, and for floating point performance,
   if you get all four processors and especially if you count on the
   new 2x processor upgrade, the 10k is a very fine piece of hardware.
[...]
   However:  (get out your ear trumpets, HP), THE DISKS cripple the   
   DN10k.

Just adding my two cents' worth here: Yes, for floating point it's a
great machine.  However I am not impressed with its interactive
response when used by several users simultaneously.  Apparently task
switching is not done frequently enough, or the algorithms for doing
so are suboptimal, for the interactive response drops rapidly as the
load average rises.  As a heavy duty number cruncher for use by a
limited number of individuals ata time, however, it is fine.  What do
they sell for these days, by the way?  Unless the price is way down
from what ours cost two years ago, it does not really seem such great
value for money any more, with everybody selling fast RISC machines at
almost PC prices.

- Harald Hanche-Olsen <hanche@imf.unit.no>
  Division of Mathematical Sciences
  The Norwegian Institute of Technology
  N-7034 Trondheim, NORWAY